Dana Farber Data Science | Training Sessions

Data Science Training Sessions cover the basics of data science and explore challenges in this growing field. These are hands-on trainings primarily conducted by department faculty and staff.

Training sessions are held either remotely using Zoom or in the Center for Life Sciences (CLSB) Building. Refer to the session details for information.
A limited number of training sessions are posted on our YouTube channel.
Notes from the training sessions are available to department members only. If you are
outside the department and would like notes from a specific training, please contact Anne ONeill.
If you are attending in person:
- Anyone without a DFCI, BWH, BCH, MGB, or Harvard ID must clear security on CLSB 2nd floor.
- Non-DFCI personnel will not have access to CLSB 11th floor. Please follow instructions posted on the doors for entry.
For questions regarding scheduling or attendance of the training sessions, contact Erica Feick.

Training Sessions 2025

To submit an evaluation for any training session you attended, please click here.

February 12, 19, 26 10:00-12:00pm	Robert Gentleman, Regression Modeling These sessions will cover least squares regression (inference, splines, diagnostics), logistic regression (inference, splines, diagnostics), and a bit on false discovery rate (FDR). The instructor will use R but attendees should easily be able to use other packages that have suitable functionality.	Hybrid, CLSB 11081 Evaluation
March 12 10:00-12:00pm	Anne O’Neill, Introduction to Clinical Trials The first part of this session provides a broad overview of phase I, II, and III clinical trials, randomization, stratification and the most common phase I design, a 5-10 minute break close to 10:45/11am, then an introduction to phase II clinical trials, collaborations with investigators and things to keep in mind when collaborating and designing, examples of some common designs and some of the in house software. In an effort to provide this material before the Phase II clinical trial design session on March 19th and to keep to the 2 hour format, this session on March 12th reviews fewer examples in detail (although all the examples would remain in the slide deck). The session on March 19th provides and reviews more examples of phase II designs.	Virtual only Evaluation
March 19 9:30-11:30am	Sandra Lee, Phase II Trial Designs The main goals of phase II clinical trials are to assess the preliminary efficacy of a new regimen and decide if the level of efficacy warrants a phase III study. The study designs of phase II studies have become more complex concerning the study endpoints, use of randomizations, and implementation of interim analyses. In this session, we will review general study considerations for phase II clinical trials and evaluate the study designs. Examples from phase II clinical trials of ECOG-ACRIN studies will be presented and discussed. Everyone is welcome and being a part of ECOG-ACRIN is not a prerequisite to attend the session.	Hybrid, CLSB 11081 Evaluation
April 2 11-12pm	Haesook Kim, Overview of Data Analysis This is an informal session providing an overview of statistical data analysis, drawing from my 30+ years of experience. This session covers topics including descriptive analysis (with an emphasis on graphical presentation), regression analysis (univariate and multivariate linear regression, logistic regression, proportional hazards regression, and common issues such as collinearity, model fitting/assessment, and bootstrapping), as well as other related analyses (missing data analysis, propensity score adjustment, PCA, correlation analysis, clustering, and more)	Hybrid, CLSB 11081 Evaluation
April 9 11-1pm	Haesook Kim, Survival Analysis I Topics included in this session are introduction of survival analysis, terminologies (event, time origin, time scale, censoring), hazard function, survival function, properties of survival time distribution, Kaplan-Meier method, calculation of confidence interval, estimation of median survival time, log-rank test, mantel-byar test. Each topic will be illustrated with numerous real data examples along with the provision of SAS and R codes. For more information on these topics, attendees are encouraged to refer to the 2023 training notes. Please note these are only available to Data Science employees; if you wish to view please contact Anne O’Neill.	Virtual only Evaluation
April 16 10-1pm	Patient Registration and Randomization at ECOG-ACRIN (with an introduction to RANCSH program for all members of DS) Session leads: Ju-Whei Lee, Amie Kim, David Hong, Yue Zheng This training session consists of two parts. Part I is to familiarize the audience with the ECOG-ACRIN Patient Registration System (PRS) software and processes, policies, procedures, timelines for study activation/modification/accrual termination, and the responsibilities of study statisticians and the PRS Team personnel in the process of various study milestones. Part I will also cover methods on how to monitor ECOG-ACRIN study accruals and examples of how to set up accrual reporting and notifications (as part of the ECOG-ACRIN study activation form) in response to various study designs. Everyone is welcome to attend this session, but this part probably is more relevant to the ECOG-ACRIN statisticians. Part II is a more general session, covering how treatments are assigned, with the focus on the method of permuted blocks for randomization and how institutional balance (if requested) works here. We’ll also demonstrate how to use the RANSCH program to generate permuted blocks for treatment assignment in randomized trials. RANSCH is a program locally available on our computing server. Anyone who is interested in learning about stratification and in using the RANSCH program is welcome to attend, being a member of ECOG-ACRIN is not a pre-requisite. For planning your time, Part II would be covered from approximately 11:40 to 1pm. There is a planned 5-10 minute break in between Part I and Part II.	Hybrid, CLSB 11081 Evaluation
June 4 10-12pm	Anne O’Neill, Introduction to Clinical Trials: Phase III Clinical Trials This is a continuation of the March 12th Introduction to Clinical Trials training session with further introduction to Phase III clinical trials, things to keep in mind when collaborating and designing, and an example using common in-house software. If time remains, further examples of trial results and stratification will be reviewed. Attendance at the March 12th Introduction to Clinical Trials session is helpful but not required.	Hybrid, CLSB 11081 Evaluation
June 11 10-12pm	Anne O’Neill, Introduction to Clinical Trials: Reading a Protocol, CRFs, database, RECIST, AE data – Part 1 This training provides an introduction to parts of the following: Protocol, Case Report Forms (CRFs), clinical trials database, RECIST criteria, and response data, all from a statistical perspective. Working with and/or viewing data is part of the session; therefore CITI certification is required. Attendance at the March 12 and June 4 Introduction to Clinical Trials Phase I,II, and III training sessions is helpful but not required.	Hybrid, CLSB 11081 Evaluation
June 18 10-11:30am	Anne O’Neill, Introduction to Clinical Trials: Reading a Protocol, CRFs, database, RECIST, AE data – Part 2 This is a continuation of the June 11th training session. This training provides an introduction to parts of the following: Common Terminology Criteria (CTCAE), clinical trials database (adverse event tables), and adverse event analyses from a statistical perspective. Working with and/or viewing data is part of the session; therefore CITI certification is required. Attendance at the March 12, June 4, and June 11 Introduction to Clinical Trials sessions is helpful but not required.	Hybrid, CLSB 11081 Evaluation
June 18 1-4pm	Erica Holdmore, Statistics for Computational Biology Projects Statistics is an important tool for computational biologists because it helps us quantitatively understand and analyze biological data. This interactive training session will cover an introduction to statistical concepts. Topics will include: experimental design, data cleaning, common analysis methods (logistic regression, ANOVA, GLM, multiple comparisons), and interpreting results.	Zoom only Evaluation
June 25 10-12pm	Jonathan Larson, Mixed Models This session will introduce linear mixed effects models, including implementation in R and interpretation of results. Theory will be presented to the extent that it aids decision-making in analysis. Registrants should have an understanding of linear regression. There is time for Q&A throughout the session and at the end.	Zoom only Evaluation
July 16 1-4pm	Jared Brown, Deeper Differential Expression Analysis with Shrinkage Correction Differential expression (alternately abundance) analysis is regularly a core tool in identifying and quantifying differences between and across groups in -omics data. In this workshop session with follow-along analysis scripts we will take a deeper look at the models underlying differential expression analysis with the particular example being the DESeq2 framework. We will examine questions around design specification, the proper use of pre-computed offsets like normalization corrections, parameter estimation and testing, and robust false discovery rate correction through post-hoc shrinkage. Examples highlighting how these approaches differ across datasets will be drawn from bulk RNAseq, single-cell RNAseq, and ChIPseq.	Zoom only Evaluation
September 9 10am-11:30pm	Anne O’Neill, INFORM Clinical Trials Database (Introduction to Access and Authorization) INFORM houses data from DF/HCC clinical trials which utilize electronic data capture (eDC). This training will provide a general overview of the INFORM Clinical Trials Database itself, from a statistical perspective, as well as the set-up needed to access data, including how to obtain authorization. Documentation for the available programs to interact with and pull data is also provided. This training is relevant to you if you are assigned to a clinical trial whose corresponding clinical data are in INFORM and you have not yet verified your access or authorization. Please reach out to Anne ONeill if you have questions about the training or if it would be applicable to the work that you do.	Hybrid, CLSB 11065 Registration
September 10 10am-12pm	Jonathan Larson, Generalized Linear Mixed Effects Models This session will extend the material from the Mixed Models training on June 25 (available at https://youtu.be/AY4FrL0xb4Q) to outcomes that are not normally distributed, e.g., count and binary outcomes. To recap, mixed models are one method for analyzing correlated data. This can include longitudinal data, when multiple observations are taken on the same unit over time; hierarchical data, such as when multiple patients are seen by the same doctor; and other forms of grouped data. We will cover implementation in R with a real data set and enough theory to guide decision-making. We strongly encourage in-person attendance.	Hybrid, CLSB 11081 Registration
September 17 10am-12pm	Brian Silverstein, Introduction to Unix	Hybrid, CLSB 11081 Registration
October 1 10am-12pm	Erica Feick, Time Management: Strategies for Productivity and Focus In today’s world, managing time effectively is more critical than ever. This talk explores the art and science of time management, offering actionable strategies to help you shift your focus from being busy to being effective. We will delve into established productivity methods (for example, GTD, Pomodoro, time blocking) and provide strategies to maintain focus in a world full of distractions. Whether you’re looking to reduce stress, improve productivity, or make better decisions, this session will equip you with the tools to take control of your time and achieve your goals. Learn ways to transform the way you manage your most valuable resource—your time.	Hybrid, CLSB 11081 Registration
October 8 10am-12pm	Miki Horiguchi, Insights from Journal Reviewers and Editors	Hybrid, CLSB 11081 Registration
October 15 10am-12pm	Jonathan Larson, Generalized Estimating Equations (GEE) This session will cover a method for analyzing correlated data that is entirely distinct from mixed models. GEE is semi-parametric, whereas mixed models are fully parametric, and GEE estimates marginal parameters, whereas mixed models (usually) estimate conditional parameters. Because we will compare and contrast these two major approaches, it will be helpful for participants to have attended the training sessions on June 25 and September 10 or watched their videos. However, understanding mixed models is not a prerequisite for understanding GEE. We will cover implementation in R with a real data set and enough theory to guide decision-making. We strongly encourage in-person attendance.	Hybrid, CLSB 11081 Registration
November 5 10am-12pm	Hajime Uno / Angel Cronin, Restricted Mean Survival Time Part I	Hybrid, CLSB 11081
November 12 10am-12pm	Hajime Uno / Angel Cronin, Restricted Mean Survival Time Part II	Hybrid, CLSB 11081

2024

Training Sessions 2024

To submit an evaluation for any training session you attended, please click here.

December 18	10-12pm	Filippo Gambarota, Introduction to Multiverse Meta-Analysis In this session we will introduce the concept of multiverse analysis applied to meta-analysis from an exploratory and inferential point of view. Multiverse analysis is a recently developed approach where given a certain research question and a dataset, authors conduct and report all plausible statistical analyses. Usually only one analysis is reported and the impact of other plausible alternatives (researcher’s degrees of freedom) on the final results is often neglected. We will see some exploratory statistics and plots and the implementation in R. The increase in complexity due to reporting multiple analysis results on the same dataset need not only descriptive methods but valid inferential approaches. We will present some methods for statistical inference in a multiverse analysis such as the specification curve, and the PIMA (post-selection inference in multiverse analysis) with the related R code. Knowledge of the R software, multiple testing and p-value adjustment methods is helpful but not required to attend these sessions. Attendees with biostatistics and computational biology background would find this applicable to their work.	Hybrid Register.
	1-3pm	Jeremy Simon, Introduction to scRNA-seq and Data Preprocessing There are many useful applications of single-cell or single-nucleus RNA-seq technologies to better understand cancer biology. In this introductory workshop, we will discuss some of the advantages of adopting single-cell approaches, frequently utilized technologies/platforms, best practices for experimental design, and provide an overview of algorithms used for data preprocessing. We will then provide an interactive demonstration of single-cell/single-nucleus RNA-seq data preprocessing with alevin-fry, resulting in a counts matrix ready for downstream analysis	Virtual Register through HBC
October 3	12:00-1:30pm	Anne O’Neill, INFORM Clinical Trials Database Part II (what happens before, during, after authorization from ODQ) This INFORM session is a continuation of the session from September 12, 2024. (Attending the September 12th session is helpful but not a requirement.) You have submitted or obtained authorization to access data from ODQ for the trial for which are you the assigned statistician, now what? This session covers examples re: the collaborative process with the medical side of the research team before, during, and after obtaining the biostat authorization/access from ODQ, i.e. examples of reasons for a statistician to pull data, things to keep in mind in the collaborative process related to the reasons for pulling data, and examples of standard emails sent by ODQ (when the ‘Data Request’ is submitted by the research team) to be reviewed as a context. This training is relevant to you if are assigned to a clinical trial whose corresponding clinical data are in INFORM database. Please reach out to Anne ONeill if you have questions about the training or if it would be applicable to the work that you do.	Virtual Email Anne O’Neill for Zoom link
September 12	11:30-1:30pm	Anne O’Neill, INFORM Clinical Trials Database (Introduction to Access and Authorization) INFORM houses data from DFHCC clinical trials which utilize electronic data capture (eDC). A general overview of the INFORM Clinical Trials Database itself from statistical perspective, the set-up needed to access data, and how to obtain authorization to access data itself from the INFORM database itself is reviewed. Documentation for the available programs to interact with and pull data from INFORM database is also provided. This training is relevant to you if are assigned to a clinical trial whose corresponding clinical data are in INFORM and you have not yet verified your access or authorization. Please reach out to Anne ONeill if you have questions about the training or if it would be applicable to the work that you do.	Virtual Evaluation
May 22	10-12pm	Jared Brown, Deeper Differential Expression Analysis with Shrinkage Correction Differential expression (alternately abundance) analysis is regularly a core tool in identifying and quantifying differences between and across groups in -omics data. In this workshop session with follow-along analysis scripts we will take a deeper look at the models underlying differential expression analysis with the particular example being the DESeq2 framework. We will examine questions around design specification, the proper use of pre-computed offsets like normalization corrections, parameter estimation and testing, and robust false discovery rate correction through post-hoc shrinkage. Examples highlighting how these approaches differ across datasets will be drawn from bulk RNAseq, single-cell RNAseq, and ChIPseq.	Hybrid, CLSB 11081 Evaluation
April 24	10-12pm	Shawn Mims and Love Nickerson, Research Administration and You How research administrators support you in your research. Presenters will discuss the nuts and bolts of grants, compliance, and beyond. This is intended for all who collaborate: faculty, post docs, statisticians, and computational biologists.	Hybrid, CLSB 11081 Evaluation
April 17	10-12pm	Mark Soliman, Intro to Git and Github We’ll go over the motivation behind version control systems (like Git) as well as some basic commands. We’ll also go over using GitHub as a repository.	Virtual Evaluation
April 10	10-12pm	Selvi Guharaj, DFCI – Data Science Centralized Data Access and Sharing The session topics include: Overview of the DFCI – Data Science (DS) Data Catalog (i.e. genomic/bioinformatics annotation databases that are downloaded and organized (i.e. GDC, GTEx, AnVIL/Terra, GEO, HCA, HTAN, NCBI, IGSR, dbGaP, 10x, GENCODE, ENSEMBL and such). Forms and procedures to request access to in-house open-/controlled-access datasets under our DFCI – DS systems and to download of new open-/controlled-access datasets under DFCI – DS centralized directories or individual lab file shares Forms and procedures on controlled-access data access: sharing of primary data files and sharing of genomic summary data files	Hybrid, CLSB 11081 Evaluation
April 3	10:30-12pm	Anne O’Neill, Introduction to Clinical Trials – General Overview The following topics are reviewed (but not limited to): various types of clinical trials, various phases of clinical trials, how are clinical trials funded, the clinical trials development process, ‘positive’ and ‘negative’ clinical trials, what types of trials are most common, roles of the different divisions within Data Science in clinical trials and related cancer projects, databases for clinical trials data, collaborations with other departments in and outside of DFCI in relation to the clinical trials and related cancer projects.	Hybrid, CLSB 11081 Evaluation
March 27	10-12pm	Erica Holdridge, Statistics for Computational Biology Projects Statistics is an important tool for computational biologists because it helps us quantitatively understand and analyze biological data. This interactive training session will cover an introduction to statistical concepts. Topics will include: experimental design, data cleaning, common analysis methods (logistic regression, ANOVA, multiple comparisons), and interpreting results.	Virtual (option of watch party) Evaluation Video
March 20	10-12pm	Sandra Lee, Phase II Trial Designs We will review general study considerations for phase II trials and evaluate the study designs. Examples from phase II trials of ECOG-ACRIN studies will be presented and discussed.	Hybrid, CLSB 11081 Evaluation
March 13	10-12pm	Yujie Guo, Introduction to scRNA-seq Data Analysis and Interpretation Using Seurat Seurat is an R package designed for QC, analysis, and exploration of single-cell RNA-seq data. It has been widely used in both dry lab and wet lab settings for its robustness and scalability. In this coding workshop, we will demonstrate the workflow of Seurat, use published matched tumor-normal data, and have hands-on experience of analyzing and interpreting such information.	Hybrid, CLSB 11081 Evaluation Video
March 6	10-12pm	Giovanni Parmigiani, Basics of Replicability In this session, we will discuss the data emerging from the “manyLabs” study of replicability of cancer biology investigations, and review remedies and good statistical practices to prevent lapses of replicability. We will revisit Simpson’s paradox, Batch effects, Shrinkage and p-hacking from a replicability perspective. You will not necessarily learn new techniques but hopefully you will learn to be on the alert for pitfalls that can do a lot of damage to the quality of your work.	Hybrid, CLSB 11081 Evaluation
February 29	10:30-12:30pm	Nabihah Tayob, Biomarkers in Cancer Research In this session, we will cover some important foundational topics when studying biomarkers in cancer research including how to evaluate a biomarker, the importance of the clinical context, designing a retrospective biomarker evaluation study and a discussion of biomarker-driven clinical trial design.	Hybrid, CLSB 11081 Evaluation Video
February 28	10-12pm	Jeremy Simon, Introduction to scRNA-seq and Data Preprocessing There are many useful applications of single-cell or single-nucleus RNA-seq technologies to better understand cancer biology. In this introductory workshop, we will discuss some of the advantages of adopting single-cell approaches, frequently utilized technologies/platforms, best practices for experimental design, and provide an overview of algorithms used for data preprocessing. We will then provide an interactive demonstration of single-cell/single-nucleus RNA-seq data preprocessing with alevin-fry, resulting in a counts matrix ready for downstream analysis	Hybrid, CLSB 11081 Evaluation Video
February 21	10-12pm	Robert Shear, R and RStudio Quickstart for Data Science Professionals For Biostatisticians, Computational Biologists and Data Scientists familiar with R who wish to more rapidly improve their R language skills. This workshop, spanning two hours with an additional optional hour for lab and discussion, will delve a step deeper into R’s essential features and functions beyond the introductory level. The session will also address debugging strategies, basic best practices, and valuable tips. Please refer to the syllabus for further information.	Hybrid, CLSB 11081 Evaluation Video
January 17	10-12pm	Nikos George, Introduction to Unix and DS-Computing In the first part, we will cover basic Unix commands, how to work with directories and files, how to navigate the Unix filesystem and how to review and change file permissions. In the second part, we will give an overview of our computing systems, and how to work with our High Performance Cluster using slurm.	Hybrid, CLSB 11081 Evaluation
January 16	2:30-4pm	Anne O’Neill, INFORM Clinical Trials Database (Introduction to Access and Authorization) INFORM houses data from DFHCC clinical trials which utilize electronic data capture (eDC). A general overview of the INFORM Clinical Trials Database itself from statistical perspective, the set-up needed to access data, and how to obtain authorization to access data itself from the INFORM database itself is reviewed. Documentation for the available programs to interact with and pull data from INFORM database is also provided. This training is relevant to you if are assigned to a clinical trial whose corresponding clinical data are in INFORM and you have not yet verified your access or authorization. Please reach out to Anne ONeill if you have questions about the training or if it would be applicable to the work that you do.	Hybrid, CLSB 11065 Evaluation

2023

Training Sessions 2023

January 11	10-12pm	Rafael Irizarry, Introduction to ggplot	In-person only, CLSB 11081
January 18	10-12pm	Rafael Irizarry, Introduction to dplyr	Hybrid, CLSB 11065
March 1	10-12pm	James Lindsay, Introduction to Python Click to Join Add to calendar	Hybrid, CLSB 11081
March 15	10-12pm	Rafael Irizarry, Jenna Landry, Document preparation with R markdown, Quarto and knitr Click to Join Add to calendar	Hybrid, CLSB 11081
March 22	10-12pm	Sandra Lee, Introduction to Phase II Clinical Trial Design Click to Join Add to Google calendar	Virtual only
April 5	10-12pm	R, Sharing Suggestions and Pointers This will be a group-led interactive session where people share tips and suggestions about packages in R that they use. Anyone is welcome to share and/or listen and learn (including sharing something from a platform other than R if time allows.) Click to Join Add to Google Calendar	Virtual only
May 17, 24, 31	12-2pm	Haesook Kim, Survival Analysis and Competing Risks Data Analysis Click to Join Add to Google Calendar	Hybrid, CLSB 11081 Lunch included with this session.
June 14	10-12pm	Susanna Jacobus, Yinglu Zhou, Zihe Song, Introduction to ct.gov Click to Join Add to Google Calendar	Hybrid, CLSB 11081
June 23 (Friday)	10-12pm	Hajime Uno, Mixed Models Click to Join Add to Google Calendar	Virtual only
June 28	12-2pm	Haesook Kim, Competing Risks Data Analysis Click to Join	Hybrid, CLSB 11081 Lunch included with this session.

Training Materials

Materials are available in the DS Training Sessions Shared Google Drive (only accessible by Data Science employees)
A limited number of training sessions are posted on our YouTube channel.
Email Anne ONeill if you would like to request materials from a training session.